Improve Config Documentation (#351)

This PR adds a utility script that generates config documentation from pgcat.toml. Ideally, we'd want to generate the configs directly from config.rs where the actual defaults are set but this is a good start as we already had several undocumented config flags.

pgcat.toml

@@ -18,21 +18,21 @@ enable_prometheus_exporter = true
 prometheus_exporter_port = 9930
 
 # How long to wait before aborting a server connection (ms).
-connect_timeout = 5000
+connect_timeout = 5000 # milliseconds
 
 # How long an idle connection with a server is left open (ms).
-idle_timeout = 30000
+idle_timeout = 30000 # milliseconds
 
 # How much time to give the health check query to return with a result (ms).
-healthcheck_timeout = 1000
+healthcheck_timeout = 1000 # milliseconds
 
 # How long to keep connection available for immediate re-use, without running a healthcheck query on it
-healthcheck_delay = 30000
+healthcheck_delay = 30000 # milliseconds
 
 # How much time to give clients during shutdown before forcibly killing client connections (ms).
-shutdown_timeout = 60000
+shutdown_timeout = 60000 # milliseconds
 
-# For how long to ban a server if it fails a health check (seconds).
+# How long to ban a server if it fails a health check (seconds).
 ban_time = 60 # seconds
 
 # If we should log client connections
@@ -41,40 +41,52 @@ log_client_connections = false
 # If we should log client disconnections
 log_client_disconnections = false
 
-# Reload config automatically if it changes.
+# When set to true, PgCat reloads configs if it detects a change in the config file.
 autoreload = false
 
 # Number of worker threads the Runtime will use (4 by default).
 worker_threads = 5
 
-# TLS
+# Number of seconds of connection idleness to wait before sending a keepalive packet to the server.
+tcp_keepalives_idle = 5
+# Number of unacknowledged keepalive packets allowed before giving up and closing the connection.
+tcp_keepalives_count = 5
+# Number of seconds between keepalive packets.
+tcp_keepalives_interval = 5
+
+# Path to TLS Certficate file to use for TLS connections
 # tls_certificate = "server.cert"
+# Path to TLS private key file to use for TLS connections
 # tls_private_key = "server.key"
 
-# Credentials to access the virtual administrative database (pgbouncer or pgcat)
+# User name to access the virtual administrative database (pgbouncer or pgcat)
 # Connecting to that database allows running commands like `SHOW POOLS`, `SHOW DATABASES`, etc..
 admin_username = "admin_user"
+# Password to access the virtual administrative database
 admin_password = "admin_pass"
 
-# pool
-# configs are structured as pool.<pool_name>
-# the pool_name is what clients use as database name when connecting
-# For the example below a client can connect using "postgres://sharding_user:sharding_user@pgcat_host:pgcat_port/sharded_db"
+# pool configs are structured as pool.<pool_name>
+# the pool_name is what clients use as database name when connecting.
+# For a pool named `sharded_db`, clients access that pool using connection string like
+# `postgres://sharding_user:sharding_user@pgcat_host:pgcat_port/sharded_db`
 [pools.sharded_db]
 # Pool mode (see PgBouncer docs for more).
-# session: one server connection per connected client
-# transaction: one server connection per client transaction
+# `session` one server connection per connected client
+# `transaction` one server connection per client transaction
 pool_mode = "transaction"
 
-# If the client doesn't specify, route traffic to
-# this role by default.
-#
-# any: round-robin between primary and replicas,
-# replica: round-robin between replicas only without touching the primary,
-# primary: all queries go to the primary unless otherwise specified.
+# Load balancing mode
+# `random` selects the server at random
+# `loc` selects the server with the least outstanding busy conncetions
+load_balancing_mode = "random"
+
+# If the client doesn't specify, PgCat routes traffic to this role by default.
+# `any` round-robin between primary and replicas,
+# `replica` round-robin between replicas only without touching the primary,
+# `primary` all queries go to the primary unless otherwise specified.
 default_role = "any"
 
-# Query parser. If enabled, we'll attempt to parse
+# If Query Parser is enabled, we'll attempt to parse
 # every incoming query to determine if it's a read or a write.
 # If it's a read query, we'll direct it to a replica. Otherwise, if it's a write,
 # we'll direct it to the primary.
@@ -93,23 +105,26 @@ primary_reads_enabled = true
 
 # So what if you wanted to implement a different hashing function,
 # or you've already built one and you want this pooler to use it?
-#
 # Current options:
-#
-# pg_bigint_hash: PARTITION BY HASH (Postgres hashing function)
-# sha1: A hashing function based on SHA1
-#
+# `pg_bigint_hash`: PARTITION BY HASH (Postgres hashing function)
+# `sha1`: A hashing function based on SHA1
 sharding_function = "pg_bigint_hash"
 
 # Automatically parse this from queries and route queries to the right shard!
-automatic_sharding_key = "data.id"
+# automatic_sharding_key = "data.id"
 
 # Idle timeout can be overwritten in the pool
 idle_timeout = 40000
 
-# Credentials for users that may connect to this cluster
+# Connect timeout can be overwritten in the pool
+connect_timeout = 3000
+
+# User configs are structured as pool.<pool_name>.users.<user_index>
+# This secion holds the credentials for users that may connect to this cluster
 [pools.sharded_db.users.0]
+# Postgresql username
 username = "sharding_user"
+# Postgresql password
 password = "sharding_user"
 # Maximum number of server connections that can be established for this user
 # The maximum number of connection from a single Pgcat process to any database in the cluster
@@ -117,6 +132,7 @@ password = "sharding_user"
 pool_size = 9
 
 # Maximum query duration. Dangerous, but protects against DBs that died in a non-obvious way.
+# 0 means it is disabled.
 statement_timeout = 0
 
 [pools.sharded_db.users.1]
@@ -125,28 +141,26 @@ password = "other_user"
 pool_size = 21
 statement_timeout = 15000
 
-# Shard 0
+# Shard configs are structured as pool.<pool_name>.shards.<shard_id>
+# Each shard config contains a list of servers that make up the shard
+# and the database name to use.
 [pools.sharded_db.shards.0]
-# [ host, port, role ]
-servers = [
-    [ "127.0.0.1", 5432, "primary" ],
-    [ "localhost", 5432, "replica" ]
-]
+# Array of servers in the shard, each server entry is an array of `[host, port, role]`
+servers = [["127.0.0.1", 5432, "primary"], ["localhost", 5432, "replica"]]
+
+# Array of mirrors for the shard, each mirror entry is an array of `[host, port, index of server in servers array]`
+# Traffic hitting the server identified by the index will be sent to the mirror.
+# mirrors = [["1.2.3.4", 5432, 0], ["1.2.3.4", 5432, 1]]
+
 # Database name (e.g. "postgres")
 database = "shard0"
 
 [pools.sharded_db.shards.1]
-servers = [
-    [ "127.0.0.1", 5432, "primary" ],
-    [ "localhost", 5432, "replica" ],
-]
+servers = [["127.0.0.1", 5432, "primary"], ["localhost", 5432, "replica"]]
 database = "shard1"
 
 [pools.sharded_db.shards.2]
-servers = [
-    [ "127.0.0.1", 5432, "primary" ],
-    [ "localhost", 5432, "replica" ],
-]
+servers = [["127.0.0.1", 5432, "primary" ], ["localhost", 5432, "replica" ]]
 database = "shard2"